WO2018149115A1

WO2018149115A1 - Method and apparatus for providing search results

Info

Publication number: WO2018149115A1
Application number: PCT/CN2017/100474
Authority: WO
Inventors: 刘国庆; 贾银芳; 朱延峰; 韩聪; 韩友; 李鹏; 党悦然; 陈敏
Original assignee: 百度在线网络技术（北京）有限公司
Priority date: 2017-02-15
Filing date: 2017-09-05
Publication date: 2018-08-23
Also published as: CN106874467B; EP3579124A4; EP3579124A1; US20190370305A1; US11669579B2; CN106874467A; JP2020507861A; JP6864107B2

Abstract

Disclosed are a method and apparatus for providing search results. One particular embodiment of the method comprises: carrying out search intention analysis on an input search term so as to determine whether the search term includes an answer requirement (201); if so, using the search term to retrieve answer content corresponding to the answer requirement (202); obtaining content to be recommended associated with the answer content (203); and combining the answer content with the content to be recommended so as to generate at least one search result (204). The embodiment can efficiently provide abundant search results.

Description

Method and apparatus for providing search results

Cross-reference to related applications

The present application claims the priority of the Chinese Patent Application No. JP-A-------

Technical field

The present application relates to the field of computer technologies, and in particular, to the field of search technologies, and in particular, to a method and apparatus for providing search results.

Background technique

With the development of Internet technology, users' search requirements for question and answer information are increasing. In the current search technology, the answer matching the user's question is displayed in the search result item in the middle of the page, and the recommended content (such as the side of the page or the bottom of the page) is separately displayed at a fixed position of the page. In this way, the answers and recommended content obtained by the user search are more scattered. And because of the limitation of the page display area, the information that the user can obtain in a search result page is very limited. If you want to obtain more information, you need to perform page switching, click filtering, search word switching, etc. on the terminal to provide information for the user. The efficiency needs to be improved.

Summary of the invention

In order to address one or more technical problems in the background, the present application provides methods and apparatus for providing search results.

In one aspect, the present application provides a method for providing search results, including: performing search intent analysis on an input search term to determine whether a search term contains a solution requirement; and if so, using the search term to retrieve a response request The content of the solution; the content to be recommended associated with the solution content; the combination of the solution content and the content to be recommended to generate at least one search result.

In some embodiments, performing search intent analysis on the input search term to determine whether the search term includes a solution requirement, including: matching the search term with a preset question keyword library; and if the matching is successful, determining the search The word contains the solution requirements.

In some embodiments, performing the search intent analysis on the input search term to determine whether the search term includes a solution requirement, including: obtaining a historical search result of the search term and category information of the historical search result; and responding to determining the acquired The category information is a question or answer category or a content recommendation category, and the search term is determined to include the answer requirement.

In some embodiments, the obtaining the to-be-recommended content associated with the solution content includes: extracting a keyword corresponding to the solution requirement in the solution content; and performing the extracted keyword and the preset keyword configured by the preset recommendation content. Matching; determining the preset recommended content corresponding to the successfully matched preset keyword as the to-be-recommended content associated with the solution content.

In some embodiments, combining the solution content with the content to be recommended to generate at least one search result includes: combining the extracted keyword with the corresponding preset recommendation content to generate a corresponding search result.

In some embodiments, the above method further comprises: pushing each search result.

In some embodiments, pushing the search results of the various items includes: pushing each search result to a search result page for display; and/or creating a link for pointing to a page containing the plurality of search results, and pushing The above link.

In a second aspect, the present application provides an apparatus for providing search results, including: an analyzing unit configured to perform search intent analysis on an input search term to determine whether a search term includes a solution request; a retrieval unit, configuration And in response to determining that the search term includes a solution requirement, using the search term to retrieve a solution content corresponding to the solution requirement; the obtaining unit configured to acquire the to-be-recommended content associated with the solution content; and the generating unit configured to use the solution content To combine the recommended content to generate at least one search result.

In some embodiments, the analysis unit is further configured to determine whether the search term includes a search requirement by matching the search term with a preset question keyword library; if the match is successful, determining that the search term includes a solution requirement.

In some embodiments, the analyzing unit is further configured to determine whether the search term includes a search requirement by acquiring a historical search result of the search term and category information of the historical search result; and responding to determining that the acquired category information is a question and answer class Or content push Recommended class to determine the search term contains the answer to the request.

In some embodiments, the obtaining unit is further configured to acquire the to-be-recommended content associated with the solution content by extracting keywords corresponding to the solution requirements in the solution content; and extracting the extracted keywords and the preset recommended content. The configured preset keyword is matched; the preset recommended content corresponding to the successfully matched preset keyword is determined as the to-be-recommended content associated with the solution content.

In some embodiments, the generating unit is further configured to generate at least one search result by combining the extracted keyword with the corresponding preset recommended content to generate a corresponding search result.

In some embodiments, the apparatus further includes: a pushing unit configured to push each search result.

In some embodiments, the push unit is further configured to push each search result by: pushing each of the search results: pushing each of the search results to a search result page for display; and/or creating A link to a page that contains multiple search results and push the link.

In a third aspect, the application provides a server comprising: one or more processors; a storage device for storing one or more programs, when one or more programs are executed by one or more processors, such that one Or a plurality of processors implement a method for providing search results as provided by the first aspect of the present application.

In a fourth aspect, the present application provides a computer readable storage medium having stored thereon a computer program that, when executed by a processor, implements a method for providing search results as provided by the first aspect of the present application.

The method and apparatus for providing search results provided by the present application, by performing search intent analysis on a search term to determine whether the search term contains a solution requirement, and then using the search term to retrieve and answer the request when determining that the input search term contains the solution request Corresponding answer content, and then obtaining the content to be recommended associated with the solution content, and finally combining the solution content with the content to be recommended, generating at least one search result, and being able to quickly provide rich search results satisfying the potential needs of the user.

DRAWINGS

Other features, objects, and advantages of the present application will become more apparent from the detailed description of the accompanying drawings.

1 is an exemplary system architecture diagram to which the present application can be applied;

2 is a flow diagram of one embodiment of a method for providing search results in accordance with the present application;

3 is a flow diagram of a specific embodiment of a method of determining whether a search term contains a solution requirement in accordance with the present application;

4 is a flow diagram of another embodiment of a method for providing search results in accordance with the present application;

5a, 5b, and 5c are schematic diagrams of effects of an application scenario for providing search results according to the present application;

6 is a schematic structural diagram of an embodiment of an apparatus for providing search results of the present application;

FIG. 7 is a schematic structural diagram of a computer system suitable for implementing a terminal device or a server of an embodiment of the present application.

detailed description

The present application will be further described in detail below with reference to the accompanying drawings and embodiments. It is understood that the specific embodiments described herein are merely illustrative of the invention, rather than the invention. It is also to be noted that, for the convenience of description, only the parts related to the related invention are shown in the drawings.

It should be noted that the embodiments in the present application and the features in the embodiments may be combined with each other without conflict. The present application will be described in detail below with reference to the accompanying drawings.

FIG. 1 illustrates an exemplary system architecture 100 of an embodiment of a method for providing search results or for providing search results to which the present application may be applied.

As shown in FIG. 1, system architecture 100 can include

terminal devices

101, 102, 103, network 104, and server 105. The network 104 is used to provide a medium for communication links between the

terminal devices

101, 102, 103 and the server 105. Network 104 may include various types of connections, such as wired, wireless communication links, fiber optic cables, and the like.

The user can interact with the server 105 over the network 104 using the

terminal devices

101, 102, 103 to receive or transmit messages and the like. Various information acquisition applications such as a web browser class, a search application, social platform software, and the like can be installed on the

terminal devices

101, 102, and 103.

The

terminal devices

101, 102, 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablets, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III, dynamic The video specialist compresses the standard audio layer 3), MP4 (Moving Picture Experts Group Audio Layer IV) player, laptop portable computer and desktop computer, and the like.

The server 105 may be a server that provides various services, such as a web page data server that provides data support for search requests of the

terminal devices

101, 102, 103. The webpage data server may perform processing such as word segmentation, webpage information capture, etc. on the received search request, and feed back the processing result (for example, the search result) to the terminal device.

It should be noted that the method for providing search results provided by the embodiments of the present application is generally performed by the server 105. Accordingly, the apparatus for providing search results is generally disposed in the server 105.

It should be understood that the number of terminal devices, networks, and servers in Figure 1 is merely illustrative. Depending on the implementation needs, there can be any number of terminal devices, networks, and servers.

With continued reference to FIG. 2, a flow 200 of one embodiment of a method for providing search results in accordance with the present application is illustrated. The method for providing search results includes the following steps:

Step 201: Perform a search intent analysis on the input search term to determine whether the search term contains a solution requirement.

In this embodiment, the electronic device (for example, the server 105 shown in FIG. 1) on which the method for providing search results is run may acquire a search term input by the user, analyze and process the search term, and then determine the search term. Whether to include the answer requirement, that is, whether the user who inputs the search term has the need to obtain an answer through a question.

Usually, users can use the input interface provided by the browser to input search terms and search using search engines. The input interface may be, for example, a search box, and the user may input a search term by typing a text; the input interface may also be, for example, an audio interface, and the user may In order to input voice information through the audio interface, the electronic device background can convert the voice information into corresponding text search words. The above electronic device may acquire the input search term after detecting that the input interface is called.

After obtaining the input search word, the electronic device may first segment the obtained search word, divide the input search form into separate words, and use the search word based on the word segmentation result and the sequence form to the user. The search intent is analyzed.

In the present embodiment, the above search intent analysis can be performed in various ways. For example, the search intent corresponding to the search term may be analyzed by using a trained search intent analysis model in a machine learning manner. Another alternative is to analyze whether the user has a preset category based on the search intent contained in the word segmented by the search term and its related words. In some optional implementation manners, the foregoing preset categories may be configured in advance for each word, such as a problem class, a resource class, and the like. For example, words such as "where", "what", "when" may be pre-configured as problem classes, and words such as "download", "view" may be pre-configured as resource classes. If the word segmentation result contains a word configured as a question class, it can be determined that the user has the requirement of the problem class, and it can be determined that the search term input by the user includes the solution requirement.

In some optional implementations, whether the input search term has a solution requirement can be analyzed by matching the search term with a preset question keyword library; if the match is successful, determining that the search term includes the solution requirement. Specifically, the foregoing electronic device may store a preset problem keyword library, and if the search word includes a word that matches a word in the preset question keyword library, it may be determined that the search word includes a solution requirement. The preset keyword library may include words that have strong relevance to the questioning intention. As an example, in the actual scenario, if the search term input by the user is “a gift recommendation for the elders”, wherein “recommended” matches the question keyword in the preset question keyword library, the search term may be determined. "Recommended gifts for elders" contains answers to your needs. Further optionally, the preset problem keyword library may be a thesaurus that is manually configured or trained based on a machine learning method and directly related to the solution requirement or has a potential solution requirement.

Please refer to FIG. 3, which shows a schematic diagram of a process 300 of a specific embodiment of a method for determining whether a search term contains a solution requirement in accordance with the present application.

As shown in FIG. 3, in step 301, a historical search result of the search term and a calendar are obtained. Category information for historical search results.

The above electronic device can store historical search results of each search term. The determining, by the electronic device, the historical search result of the search term acquired in step 201 in the stored large number of historical search results, and determining the category information of the historical search result. The above category information may include a question and answer class, a content recommendation class, a resource class, and the like. The category information of each historical search result may be determined by the source website of the historical search result, the category of the content, and the like. Further, the category information of each historical search result may be related to the category information of the source website of the historical search result or the history. The category information of the content of the search results is consistent. For example, if the source website of a historical search result is "Baidu Know" and the category information of "Baidu Know" is a question and answer class, it can be determined that the category information of the historical search result is a question and answer class; or if a historical search is performed The result includes a dialogue of multiple question and answer sentences, then it can be determined that the category information of the historical search result is a question and answer class; or when a historical search result contains multiple recommended contents (in other words, the historical search word triggers the content recommendation) And determining that the content of the historical search result is a content recommendation class, the category information of the historical search result may be further determined to be a content recommendation class. In some implementations, the historical search result includes a related search formula of the search term determined by the electronic device according to a query history of a large data amount of different users, and the related search formula may be used as a historical search result, according to the related search formula. The category determines whether the search term contains a solution requirement. For example, when the relevant query contains a question, the category information of the historical search result of the search term may be determined as a question and answer class.

It should be noted that the category information of the historical search result may be pre-configured, or may be analyzed based on attributes such as the source website and content of the historical search result. The category information of each website and the category information analysis of different contents may adopt various existing analysis methods of various categories, and are not specifically limited herein.

In step 302, in response to determining that the acquired category information is a question-answer class or a content recommendation class, it is determined that the search term includes a solution requirement.

When the category information of the historical search result obtained in step 301 is a question-answer class or a content recommendation class, it may be determined that the user who inputs the search term has a potential requirement for the question, and then the search term input by the user may be determined to include the solution requirement. That is to say, if the above category information is a question-answer class or a content recommendation class, it can be determined that the user's actual search intention is to present a need Answer the question.

In a further embodiment, if the category information is not a question or answer category or a content recommendation category, it may be determined that the search term obtained in step 201 does not include a solution requirement.

The above electronic device can implement an estimation of the user's search intent to utilize the analysis result by the above process 300 for determining whether the search term includes an optional implementation of the solution requirement and other optional means for determining whether the search term contains a solution requirement. To provide information that meets the needs of users.

Returning to FIG. 2, in step 202, in response to determining that the search term contains a solution request, the search term is used to retrieve the solution content corresponding to the solution requirement.

In this embodiment, after determining that the search term includes a solution requirement, that is, determining that the user has an intention to propose a question to be answered, the electronic device may retrieve a solution content corresponding to the solution requirement in the database.

Specifically, the electronic device can directly search by using a search term, and filter out the search result of the solution class, and extract the solution content therein. Or, in the search intention analysis of the search term, the solution demand corresponding to the search term can be parsed, and the solution is obtained based on the solution requirement, and the solution content is obtained. For example, after determining the user's answering needs, the answer content corresponding to the answering requirement can be crawled in the knowledge-based website (for example, "Baidu Know"). Alternatively, the electronic device may perform a search by adding a related word and an auxiliary word according to the answer requirement to expand the search word into a query type of the question and answer type based on the search word, for example, when the input search word is “luxury bag” The search term can be expanded to search for the question and answer type of the "luxury bag brand", so that the electronic device can quickly retrieve the answer content of the search formula corresponding to the question and answer class.

Step 203: Acquire content to be recommended associated with the solution content.

In this embodiment, the electronic device may find the content to be recommended associated with the solution content in the content library to be recommended. The content to be recommended includes the content to be recommended with the recommended attribute, and the recommended attribute is used to identify the attribute of the content to be recommended. Specifically, the recommended attribute may be the feature information that can match the content to be recommended.

In some optional implementation manners, the recommended attribute may be a preset keyword configured by the content to be recommended. In this case, the content to be recommended associated with the solution content may be obtained by: first extracting the solution content corresponding to the solution Key words of demand, will be mentioned later The extracted keyword is matched with the preset keyword configured by the preset recommended content, and the preset recommended content corresponding to the successfully matched preset keyword is determined as the to-be-recommended content associated with the solution content. Specifically, the electronic device may extract one or more keywords in the solution content, and then determine whether the extracted keyword corresponds to the solution requirement, and use each of the extracted keywords corresponding to the solution requirement and each The preset keywords of the recommended content are matched. If the matching is successful, the preset recommended content corresponding to the successfully matched preset keyword is used as the to-be-recommended content corresponding to the extracted keyword, that is, the content of the solution. Associated content to be recommended. In this way, when a plurality of keywords are included in the solution content, different to-be-recommended contents corresponding to each keyword can be matched.

Optionally, the content to be recommended may be content pre-stored by the electronic device and configured with a preset keyword. These to-be-recommended content may contain richer recommendation information, which may be, for example, news information, advertisements, and the like.

Step 204: Combine the solution content with the content to be recommended, and generate at least one search result.

After obtaining the content to be recommended associated with the solution content, the content to be recommended may be combined with the corresponding solution content to generate a search result. Specifically, for a solution content retrieved in step 202, it may be combined with one or more items to be recommended associated with it to generate a search result. If the step 202 retrieves a plurality of pieces of solution content, the corresponding plurality of search results may be generated in the embodiment. The combination may be performed by combining the solution content with the associated content to be recommended, or storing the relationship between the solution content and the content to be recommended in the database. In this way, each search result contains the answer content and the related content to be recommended, so that the rich information can be quickly provided, and the user only needs to perform a search operation to obtain the answer content, that is, the related recommendation information, which simplifies the user's acquisition. The operation of the information.

In some optional implementation manners, if the keyword corresponding to the solution requirement in the solution content is extracted in step 203, the extracted keyword may be combined with the preset recommended content successfully matched to generate a corresponding search. result. That is to say, by using the keyword instead of the solution content and generating the search result in combination with the corresponding content to be recommended, the search result can be simplified, and the key information more interesting to the user is provided, which is beneficial for the user to quickly obtain the information.

Thus, the method for providing search results of the present embodiment, by analyzing the search intent of the search term, obtains the to-be-recommended content associated with the solution request when determining that the search term includes the solution request, and retrieves the retrieved content. The combination of the content of the solution and the content to be recommended generates search results, which can quickly provide more information in the search results that better meets the potential needs of users.

Please refer to FIG. 4, which shows a flowchart of another embodiment of a method for providing search results according to the present application. The method flow 400 for providing search results includes the following steps:

Step 401: Perform a search intent analysis on the input search term to determine whether the search term contains a solution requirement.

In this embodiment, the electronic device (for example, the server 105 shown in FIG. 1) on which the method for providing search results is run may acquire a search term input by the user, analyze and process the search term, and then determine the search term. Whether to include the answer requirement, that is, whether the user who inputs the search term has the need to obtain an answer through a question. Specifically, after acquiring the input search term, the electronic device may perform search intent analysis in various manners. For example, the trained search intent analysis model may be used to analyze the search intent corresponding to the search term, or the search intent included in the word segmented by the search term and the related search term may be analyzed to determine whether the user has a preset category. The requirement, or the search term can be matched with the preset question keyword library; if the match is successful, it is determined that the search term contains the solution requirement. The preset problem keyword library includes words that have strong relevance to the questioning intent. As an example, in the actual scenario, if the search term input by the user is “a gift recommendation for the elders”, wherein “recommended” matches the preset question keyword library, the search term “is given to the elders”. Gift recommendation" contains the answer to the request.

Optionally, the method further includes: determining whether the search term includes a solution requirement: acquiring a historical search result of the search term and category information of the historical search result, and responding to determining that the acquired category information is a question-answer class or a content recommendation class, Make sure the search term contains the answer to the request. That is, it is possible to determine whether the search term contains a solution request according to the source website of the historical search result of the search term, the category of the content, and the like.

Step 402, in response to determining that the search term includes a solution requirement, using the search term to retrieve a solution content corresponding to the solution requirement.

Step 403: Acquire content to be recommended associated with the solution content.

In this embodiment, the content to be recommended associated with the above solution content may be found in the content library to be recommended. For example, the relevance of the solution content and the content to be recommended may be determined by semantic analysis, and the content to be recommended with higher relevance is selected as the content to be recommended associated with the solution content. Or in some optional implementation manners, the keywords corresponding to the solution requirements in the solution content may be extracted, and then the extracted keywords are matched with the preset keywords configured by the preset recommended content, and the matching success is pre-matched. The preset recommended content corresponding to the keyword is determined as the content to be recommended associated with the answer content.

Step 404, combining the solution content with the content to be recommended, and generating at least one search result.

After obtaining the content to be recommended associated with the solution content, the content to be recommended may be combined with the corresponding solution content to generate a search result. The combination may be performed by combining the solution content with the associated content to be recommended, or storing the relationship between the solution content and the content to be recommended in the database. In this way, each search result contains the answer content and the content to be recommended associated with it.

In some optional implementation manners, if the keyword corresponding to the solution requirement in the solution content is extracted in step 203, the extracted keyword may be combined with the preset recommended content successfully matched to generate a corresponding search. result. That is to say, by using the keyword instead of the solution content and generating the search result in combination with the corresponding content to be recommended, the search result can be simplified, and the information more interesting to the user can be provided, which is beneficial for the user to quickly obtain the information.

It should be noted that the specific operations in the foregoing steps 401 to 404 are substantially the same as the specific operations in the steps 201 to 204, and details are not described herein again.

In step 405, various search results are pushed.

After generating the various search results, the electronic device (eg, server 105 shown in FIG. 1) can push the search results to a terminal device (eg,

terminal devices

101, 102, 103 shown in FIG. 1) that receives user input. The terminal device can create a search result page, and the electronic device can push the search result to the search result page for display. Terminal equipment can Render search results to the search results page for display. Multiple entry fields for presenting search results can be created within the search results page and each search result displayed in each entry column. Further, the electronic device may push the matching degree order corresponding to the search result (for example, the answer content in the search result is sorted with the matching degree of the solution requirement). In this way, the terminal device can sequentially display the corresponding search results according to the matching content of the answer content in each search result and the matching requirement of the above solution. Here, each search result includes at least one answer content and a to-be-recommended content associated with the answer content, and each of the answer content can be displayed in association with the to-be-recommended content associated with it.

In some optional implementation manners, in order to save the display space occupied by the above search result and simplify the search result page, the electronic device may push by creating a link for pointing to a page containing multiple search results and pushing the link. Various search results. In this way, the user can click on the link to open the corresponding page containing multiple search results to obtain the above search results.

Accordingly, the interrupting device is after receiving the search result pushed by the electronic device. The above search results can be displayed in a variety of presentations. An alternative implementation is to display multiple search results simultaneously on the search results page so that the user can get answers and recommendations without further action.

Please refer to FIG. 5a, which illustrates an effect diagram of an application scenario for providing search results according to the present application. After the user types the search term “What is required for military training” in the search box 501 in the browser provided by the terminal device or other searchable application, the terminal may initiate a search request to the server, and the server searches for the search term. Analysis, according to the keyword "what" contained in the search term to determine the search term contains the solution requirements, then the server can use the search term to retrieve the answer content corresponding to the solution needs: "sunscreen", "toothpaste", etc., after The server can find the content to be recommended (such as a sunscreen advertisement) associated with the sunscreen from the background content library to be recommended in the background (for example, an advertisement database), and combine the answer content "sunscreen" with the sunscreen advertisement as a search result 502. The content to be recommended (for example, toothpaste advertisement) associated with the toothpaste can be found from the background content library to be recommended (for example, an advertisement database), and the answer content “toothpaste” and the toothpaste advertisement can be combined into one search result 503. The server can then directly push the search result 502 and the search result 503 to the terminal device, and the terminal device can directly on the search result page 51. Search results 502 and search results 503 are displayed.

The search result terminal device pushed by the receiving server may also display various search results by creating a switchable tab on the search result page, and presenting each search result in each tab.

Please refer to FIG. 5b, which illustrates an effect diagram of an application scenario for providing search results according to the present application. After the user types the search term "What watch is Obama's watch" in the search box 511 in the browser provided by the electronic device or other search-enabled application, the electronic device can initiate a search request to the server, and the server performs the search term. Search intent analysis, according to the keyword "what" contained in the search term to determine the search term contains the answer needs, then the server can use the search term to retrieve the answer content corresponding to the answer: "TAG Heuer", "Jorg Gray", " Armani", after that, the server can find the corresponding profiles and advertisements of "TAG Heuer" Jorg Gray" and "Armani" watch brands from the background advertisement database, and combine the names of each watch brand with the corresponding profiles and advertisements. The search results are then pushed to the electronic device. The electronic device can create corresponding three

tabs

512, 513, 514 in the search result page 52, and display corresponding watch brand names and corresponding brand profiles in each tab. And advertising. Further, it can be done by clicking or gesture Switch tabs to make it easy for users to get different answers and associated recommendations.

In some optional implementations, if the server creates a link for a page that includes multiple search results after generating the search result, and pushes the link, the terminal device may display the push in the search result page. link. FIG. 5c is a schematic diagram showing the effect of an application scenario for providing search results according to the present application.

As shown in FIG. 5c, after the user types the search term "What is required for military training" in the search box 521 in the browser provided by the terminal device or other search-enabled application, the terminal can initiate a search request to the server, and the server searches for The word is used for search intent analysis. The search term can be determined according to the keyword “what” included in the search term. The server can use the search term to retrieve the answer content corresponding to the solution requirement: “sunscreen” and “toothpaste”. After that, the server can find the sunscreen advertisement and the toothpaste advertisement from the background advertisement database, combine the content "sunscreen" and the sunscreen advertisement into a search result, and combine the answer "toothpaste" and the toothpaste advertisement into Another search knot fruit. The server can then create a link 522 that points to the network address of page 54, which contains a search result of a combination of sunscreen and sunscreen ads and a search result formed by a combination of toothpaste and toothpaste ads. The server can push the link 522 to the terminal device that issued the search request, and the terminal device can display the link 522 in the search results page 53, which is rendered on page 54 when clicked. This can reduce the display space occupied by the search results while enriching the search results and improving the user's information acquisition efficiency.

As can be seen from the above, the flow 400 of the method for providing search results of the present embodiment increases the step 405 of pushing the search result, and by step 405, the generated search result can be pushed to the received search. The terminal device of the word is displayed for the user to obtain information efficiently.

Referring to FIG. 6, as an implementation of the method shown in the above figures, the present application provides an embodiment of an apparatus for providing search results, the apparatus embodiment corresponding to the method embodiment shown in FIG. The device can be specifically applied to various electronic devices.

As shown in FIG. 6, the apparatus 600 for providing search results of the present embodiment includes an analysis unit 601, a retrieval unit 602, an acquisition unit 603, and a generation unit 604. The analyzing unit 601 is configured to perform a search intent analysis on the input search term to determine whether the search term contains a solution requirement; the retrieving unit 602 is configured to retrieve and answer the request by using the search term in response to determining that the search term includes the solution requirement Corresponding solution content; the obtaining unit 603 is configured to acquire the to-be-recommended content associated with the solution content; the generating unit 604 is configured to combine the solution content with the content to be recommended to generate at least one search result.

In this embodiment, the analyzing unit 601 can acquire the search words input by the user, and analyze and process the search words by using a word segmentation, machine learning, and the like to determine whether the search words include the solution requirements.

When the analysis result of the determination analysis unit 601 is that the search result includes the solution requirement, the retrieval unit 602 can directly search using the search term, and filter out the retrieval result of the solution class, and extract the solution content therein. Or, in the search intention analysis of the search term, the solution demand corresponding to the search term can be parsed, and the solution is obtained based on the solution requirement, and the solution content is obtained.

The obtaining unit 603 can find the to-be-recommended content associated with the above solution content in the content library to be recommended. Among them, the content to be recommended associated with the answer content can be within the answer The semantic relevance of the content exceeds a preset threshold for the content to be recommended.

The generating unit 604 may combine the solution content and the content to be recommended associated with the solution content to generate a search result. If the retrieval unit 602 retrieves a plurality of pieces of solution content, the generating unit 604 may generate a corresponding plurality of search results in the embodiment.

In some optional implementation manners of the implementation, the analyzing unit 601 may be further configured to determine whether the search term includes a search requirement by matching the search term with a preset problem keyword library; if the matching is successful, Make sure the search term contains the answer to the request. The preset question keyword library may contain words that have strong relevance to the question intent.

In some optional implementation manners of the implementation, the analyzing unit 601 may be further configured to determine whether the search term includes a search requirement by acquiring a historical search result of the search term and category information of the historical search result; The obtained category information is a question or answer category or a content recommendation category, and the search term is determined to include the answer requirement. That is, the analyzing unit 601 can determine the category information according to the content of the historical search result of the search term, the source website, and the like. If the category information is a question answer class or a content recommendation class, it can be determined that the search term includes the search requirement.

In some optional implementation manners of the implementation, the obtaining unit 603 may be further configured to obtain the content to be recommended associated with the solution content by extracting keywords corresponding to the solution requirements in the solution content; The word is matched with the preset keyword configured by the preset recommended content; and the preset recommended content corresponding to the successfully matched preset keyword is determined as the to-be-recommended content associated with the solution content.

In a further implementation manner, the generating unit 604 is further configured to generate at least one search result by combining the extracted keyword with the corresponding preset recommended content to generate a corresponding search result.

In some optional implementations of the present implementation, the apparatus 600 further includes a push unit 605 (not shown) configured to push various search results. Further, the pushing unit 605 can be further configured to push each search result by pushing each search result to the search result page for display; and/or creating a link for pointing to a page containing multiple search results And push the link.

The above embodiment of the apparatus 600 for providing search results may analyze the user's search intent and find the to-be-recommended content associated with the retrieved answer content, which may be mentioned For richer search results, it improves the efficiency of providing information to users.

The application also provides a server that includes one or more processors, and a storage device. The storage device is for storing one or more programs, and the one or more programs stored by the storage device are executed by one or more processors, such that the one or more processors implement the above-described embodiments of the present application for providing search results. method.

Referring now to Figure 7, a block diagram of a computer system 700 suitable for use with a server for implementing embodiments of the present application is shown. The server shown in FIG. 7 is merely an example, and should not impose any limitation on the function and scope of use of the embodiments of the present application.

As shown in FIG. 7, computer system 700 includes a central processing unit (CPU) 701 that can be loaded into a program in random access memory (RAM) 703 according to a program stored in read only memory (ROM) 702 or from storage portion 708. And perform various appropriate actions and processes. In the RAM 703, various programs and data required for the operation of the system 700 are also stored. The CPU 701, the ROM 702, and the RAM 703 are connected to each other through a bus 704. An input/output (I/O) interface 705 is also coupled to bus 704.

The following components are connected to the I/O interface 705: an input portion 706 including a keyboard, a mouse, etc.; an output portion 707 including a cathode ray tube (CRT), a liquid crystal display (LCD), and the like, and a speaker; a storage portion 708 including a hard disk or the like And a communication portion 709 including a network interface card such as a LAN card, a modem, or the like. The communication section 709 performs communication processing via a network such as the Internet. Driver 710 is also connected to I/O interface 705 as needed. A removable medium 711, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory or the like, is mounted on the drive 710 as needed so that a computer program read therefrom is installed into the storage portion 708 as needed.

In particular, the processes described above with reference to the flowcharts may be implemented as a computer software program in accordance with an embodiment of the present disclosure. For example, an embodiment of the present disclosure includes a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for executing the method illustrated in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network via communication portion 709, and/or installed from removable media 711. When the computer program is executed by the central processing unit (CPU) 701, the above-described functions defined in the method of the present application are performed. It should be noted that the computer readable medium described herein may be a computer readable signal medium or a computer readable medium. The storage medium is either any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of computer readable storage media may include, but are not limited to, electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), erasable Programmable read only memory (EPROM or flash memory), optical fiber, portable compact disk read only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the foregoing. In the present application, a computer readable storage medium may be any tangible medium that can contain or store a program, which can be used by or in connection with an instruction execution system, apparatus or device. In the present application, a computer readable signal medium may include a data signal that is propagated in the baseband or as part of a carrier, carrying computer readable program code. Such propagated data signals can take a variety of forms including, but not limited to, electromagnetic signals, optical signals, or any suitable combination of the foregoing. The computer readable signal medium can also be any computer readable medium other than a computer readable storage medium, which can transmit, propagate, or transport a program for use by or in connection with the instruction execution system, apparatus, or device. . Program code embodied on a computer readable medium can be transmitted by any suitable medium, including but not limited to wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.

The flowchart and block diagrams in the Figures illustrate the architecture, functionality and operation of possible implementations of systems, methods and computer program products in accordance with various embodiments of the present application. In this regard, each block of the flowchart or block diagram can represent a module, a program segment, or a portion of code that includes one or more of the logic functions for implementing the specified. Executable instructions. It should also be noted that in some alternative implementations, the functions noted in the blocks may also occur in a different order than that illustrated in the drawings. For example, two successively represented blocks may in fact be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending upon the functionality involved. It is also noted that each block of the block diagrams and/or flowcharts, and combinations of blocks in the block diagrams and/or flowcharts, can be implemented in a dedicated hardware-based system that performs the specified function or operation. Or it can be implemented by a combination of dedicated hardware and computer instructions.

The units involved in the embodiments of the present application can be implemented by software. Now, it can also be implemented by hardware. The described unit may also be provided in the processor, for example, as a processor including an analysis unit, a retrieval unit, an acquisition unit, and a generation unit. Wherein, the names of these units do not constitute a limitation on the unit itself under certain circumstances. For example, the analysis unit may also be described as "searching for the search intention of the input search words to determine whether the search words contain the solution requirements. Unit."

In another aspect, the present application also provides a computer readable medium, which may be included in the apparatus described in the above embodiments, or may be separately present and not incorporated into the apparatus. The computer readable medium carries one or more programs, when the one or more programs are executed by the device, causing the device to: perform a search intent analysis on the input search words to determine whether the search term contains a solution requirement; If yes, the search term is used to retrieve the solution content corresponding to the solution requirement; the content to be recommended associated with the solution content is obtained; and the solution content is combined with the content to be recommended to generate at least one search result.

The above description is only a preferred embodiment of the present application and a description of the principles of the applied technology. It should be understood by those skilled in the art that the scope of the invention referred to in the present application is not limited to the specific combination of the above technical features, and should also be covered by the above technical features or without departing from the above inventive concept. Other technical solutions formed by arbitrarily combining the equivalent features. For example, the above features are combined with the technical features disclosed in the present application, but are not limited to the technical features having similar functions.

Claims

A method for providing search results, the method comprising:

Performing a search intent analysis on the input search term to determine whether the search term contains a solution requirement;

If yes, using the search term to retrieve a solution content corresponding to the solution requirement;

Obtaining to-be-recommended content associated with the answer content;

Combining the solution content with the to-be-recommended content to generate at least one search result.
The method according to claim 1, wherein said performing search intent analysis on the input search term to determine whether said search term contains a solution requirement comprises:

Matching the search term with a preset question keyword library;

If the match is successful, it is determined that the search term contains a solution requirement.
The method according to claim 1, wherein said performing search intent analysis on the input search term to determine whether said search term contains a solution requirement comprises:

Obtaining a historical search result of the search term and category information of the historical search result;

In response to determining that the acquired category information is a question or answer category or a content recommendation category, determining that the search term includes a solution requirement.
The method according to claim 1, wherein the obtaining the content to be recommended associated with the solution content comprises:

Extracting keywords corresponding to the solution requirements in the solution content;

Matching the extracted keywords with preset keywords configured by the preset recommended content;

The preset recommended content corresponding to the preset keyword that is successfully matched is determined as the content to be recommended associated with the solution content.
The method of claim 4 wherein said said solution is within Combining with the content to be recommended, generating at least one search result, including:

Combining the extracted keywords with the corresponding preset recommended content to generate a corresponding search result.
The method of claim 1 further comprising:

Push each of the search results.
The method according to claim 6, wherein said pushing said search results comprises:

Pushing each of the search results to a search results page for display; and/or

Create a link to a page that contains multiple search results and push the link.
An apparatus for providing search results, the apparatus comprising:

An analysis unit configured to perform a search intent analysis on the input search term to determine whether the search term includes a solution requirement;

a retrieval unit configured to retrieve, by the search term, a solution content corresponding to the solution requirement in response to determining that the search term includes a solution requirement;

An obtaining unit, configured to acquire content to be recommended associated with the solution content;

And a generating unit configured to combine the solution content with the to-be-recommended content to generate at least one search result.
The apparatus of claim 8, wherein the analyzing unit is further configured to determine whether the search term includes a search requirement as follows:

Matching the search term with a preset question keyword library;

If the match is successful, it is determined that the search term contains a solution requirement.
The apparatus of claim 8, wherein the analyzing unit is further configured to determine whether the search term includes a search requirement as follows:

Obtaining a historical search result of the search term and category information of the historical search result;

In response to determining that the acquired category information is a question or answer category or a content recommendation category, determining that the search term includes a solution requirement.
The apparatus according to claim 8, wherein the obtaining unit is further configured to acquire content to be recommended associated with the solution content as follows:

Extracting keywords corresponding to the solution requirements in the solution content;

Matching the extracted keywords with preset keywords configured by the preset recommended content;

The preset recommended content corresponding to the preset keyword that is successfully matched is determined as the content to be recommended associated with the solution content.
The apparatus according to claim 11, wherein said generating unit is further configured to generate at least one search result as follows:

Combining the extracted keywords with the corresponding preset recommended content to generate a corresponding search result.
The device according to claim 8, wherein the device further comprises:

a pushing unit configured to push each of the search results.
The apparatus of claim 13 wherein said push unit is further configured to push said search results as follows:

Pushing each of the search results to a search results page for display; and/or

Create a link to a page that contains multiple search results and push the link.
A server, comprising:

One or more processors;

a storage device for storing one or more programs,

The one or more programs are executed by the one or more processors such that the one or more processors implement the method of any of claims 1-7.
A computer readable storage medium having stored thereon a computer program, wherein the computer program is executed by a processor to implement the method of any of claims 1-7.